leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

leaderboard.cn

Benchmark details loading

Loading page content

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

TAU1-RetailAgents

Results for 9 models collected from 2 public sources.

#ModelScore

Qwen3-235B-A22B-Instruct-2507Alibaba

71.3%

Qwen3-235B-A22B-Thinking-2507Alibaba

67.8%

Qwen3-30B-A3B-Thinking-2507Alibaba

67.8%

Qwen3-4B-Thinking-2507Alibaba

66.1%

Qwen3-30B-A3B-Instruct-2507Alibaba

59.1%

Qwen3-4B-Instruct-2507Alibaba

48.7%

Qwen3-30B-A3BAlibaba · Initial April 2025 model · non-reasoning mode

38.3%

Qwen3-4BAlibaba · Initial April 2025 model · non-reasoning mode

24.3%

GPT-4.1 nano 2025-04-14OpenAI

23.5%

9 models total

Benchmark details loading

Back to benchmarks

TAU1-RetailAgents

Results for 9 models collected from 2 public sources.

#ModelScore

Qwen3-235B-A22B-Instruct-2507Alibaba

71.3%

Qwen3-235B-A22B-Thinking-2507Alibaba

67.8%

Qwen3-30B-A3B-Thinking-2507Alibaba

67.8%

Qwen3-4B-Thinking-2507Alibaba

66.1%

Qwen3-30B-A3B-Instruct-2507Alibaba

59.1%

Qwen3-4B-Instruct-2507Alibaba

48.7%

Qwen3-30B-A3BAlibaba · Initial April 2025 model · non-reasoning mode

38.3%

Qwen3-4BAlibaba · Initial April 2025 model · non-reasoning mode

24.3%

GPT-4.1 nano 2025-04-14OpenAI

23.5%

9 models total